{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2536461636017755,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006341154090044388,
      "eval_loss": 1.7219620943069458,
      "eval_runtime": 19.0376,
      "eval_samples_per_second": 139.513,
      "eval_steps_per_second": 17.439,
      "step": 1
    },
    {
      "epoch": 0.0031705770450221942,
      "grad_norm": 0.10843837261199951,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.6935,
      "step": 5
    },
    {
      "epoch": 0.0063411540900443885,
      "grad_norm": 0.11587362736463547,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.7519,
      "step": 10
    },
    {
      "epoch": 0.009511731135066582,
      "grad_norm": 0.11342128366231918,
      "learning_rate": 5e-05,
      "loss": 1.6728,
      "step": 15
    },
    {
      "epoch": 0.012682308180088777,
      "grad_norm": 0.15928195416927338,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.7278,
      "step": 20
    },
    {
      "epoch": 0.01585288522511097,
      "grad_norm": 0.18188682198524475,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.7063,
      "step": 25
    },
    {
      "epoch": 0.019023462270133164,
      "grad_norm": 0.14880536496639252,
      "learning_rate": 0.0001,
      "loss": 1.6,
      "step": 30
    },
    {
      "epoch": 0.02219403931515536,
      "grad_norm": 0.17781168222427368,
      "learning_rate": 9.995494831023409e-05,
      "loss": 1.5695,
      "step": 35
    },
    {
      "epoch": 0.025364616360177554,
      "grad_norm": 0.16159026324748993,
      "learning_rate": 9.981987442712633e-05,
      "loss": 1.4284,
      "step": 40
    },
    {
      "epoch": 0.028535193405199746,
      "grad_norm": 0.17558260262012482,
      "learning_rate": 9.959502176294383e-05,
      "loss": 1.3735,
      "step": 45
    },
    {
      "epoch": 0.03170577045022194,
      "grad_norm": 0.3049725890159607,
      "learning_rate": 9.928079551738543e-05,
      "loss": 1.2543,
      "step": 50
    },
    {
      "epoch": 0.03487634749524413,
      "grad_norm": 0.1540101319551468,
      "learning_rate": 9.887776194738432e-05,
      "loss": 1.2435,
      "step": 55
    },
    {
      "epoch": 0.03804692454026633,
      "grad_norm": 0.1451278030872345,
      "learning_rate": 9.838664734667495e-05,
      "loss": 1.193,
      "step": 60
    },
    {
      "epoch": 0.04121750158528852,
      "grad_norm": 0.1608607918024063,
      "learning_rate": 9.780833673696254e-05,
      "loss": 1.1337,
      "step": 65
    },
    {
      "epoch": 0.04438807863031072,
      "grad_norm": 0.12036971002817154,
      "learning_rate": 9.714387227305422e-05,
      "loss": 1.1332,
      "step": 70
    },
    {
      "epoch": 0.04755865567533291,
      "grad_norm": 0.2018367350101471,
      "learning_rate": 9.639445136482548e-05,
      "loss": 1.0513,
      "step": 75
    },
    {
      "epoch": 0.05072923272035511,
      "grad_norm": 0.10749484598636627,
      "learning_rate": 9.55614245194068e-05,
      "loss": 1.1357,
      "step": 80
    },
    {
      "epoch": 0.053899809765377296,
      "grad_norm": 0.13610756397247314,
      "learning_rate": 9.464629290747842e-05,
      "loss": 1.1014,
      "step": 85
    },
    {
      "epoch": 0.05707038681039949,
      "grad_norm": 0.12932488322257996,
      "learning_rate": 9.365070565805941e-05,
      "loss": 1.0783,
      "step": 90
    },
    {
      "epoch": 0.060240963855421686,
      "grad_norm": 0.09866411238908768,
      "learning_rate": 9.257645688666556e-05,
      "loss": 1.0815,
      "step": 95
    },
    {
      "epoch": 0.06341154090044387,
      "grad_norm": 0.1398266851902008,
      "learning_rate": 9.142548246219212e-05,
      "loss": 1.0114,
      "step": 100
    },
    {
      "epoch": 0.06341154090044387,
      "eval_loss": 1.0573999881744385,
      "eval_runtime": 19.1594,
      "eval_samples_per_second": 138.627,
      "eval_steps_per_second": 17.328,
      "step": 100
    },
    {
      "epoch": 0.06658211794546608,
      "grad_norm": 0.10083888471126556,
      "learning_rate": 9.019985651834703e-05,
      "loss": 1.1046,
      "step": 105
    },
    {
      "epoch": 0.06975269499048826,
      "grad_norm": 0.12223061919212341,
      "learning_rate": 8.890178771592199e-05,
      "loss": 1.0518,
      "step": 110
    },
    {
      "epoch": 0.07292327203551047,
      "grad_norm": 0.116086445748806,
      "learning_rate": 8.753361526263621e-05,
      "loss": 1.0418,
      "step": 115
    },
    {
      "epoch": 0.07609384908053266,
      "grad_norm": 0.10885754227638245,
      "learning_rate": 8.609780469772623e-05,
      "loss": 1.067,
      "step": 120
    },
    {
      "epoch": 0.07926442612555486,
      "grad_norm": 0.18372325599193573,
      "learning_rate": 8.459694344887732e-05,
      "loss": 0.9848,
      "step": 125
    },
    {
      "epoch": 0.08243500317057705,
      "grad_norm": 0.11185949295759201,
      "learning_rate": 8.303373616950408e-05,
      "loss": 1.0812,
      "step": 130
    },
    {
      "epoch": 0.08560558021559923,
      "grad_norm": 0.12270341068506241,
      "learning_rate": 8.141099986478212e-05,
      "loss": 1.0321,
      "step": 135
    },
    {
      "epoch": 0.08877615726062144,
      "grad_norm": 0.11881193518638611,
      "learning_rate": 7.973165881521434e-05,
      "loss": 1.0209,
      "step": 140
    },
    {
      "epoch": 0.09194673430564362,
      "grad_norm": 0.11358780413866043,
      "learning_rate": 7.799873930687978e-05,
      "loss": 1.051,
      "step": 145
    },
    {
      "epoch": 0.09511731135066583,
      "grad_norm": 0.15387596189975739,
      "learning_rate": 7.621536417786159e-05,
      "loss": 1.0115,
      "step": 150
    },
    {
      "epoch": 0.09828788839568801,
      "grad_norm": 0.11465586721897125,
      "learning_rate": 7.438474719068173e-05,
      "loss": 1.0698,
      "step": 155
    },
    {
      "epoch": 0.10145846544071022,
      "grad_norm": 0.13638044893741608,
      "learning_rate": 7.251018724088367e-05,
      "loss": 1.0234,
      "step": 160
    },
    {
      "epoch": 0.1046290424857324,
      "grad_norm": 0.14747582376003265,
      "learning_rate": 7.059506241219965e-05,
      "loss": 1.023,
      "step": 165
    },
    {
      "epoch": 0.10779961953075459,
      "grad_norm": 0.12780265510082245,
      "learning_rate": 6.864282388901544e-05,
      "loss": 1.0459,
      "step": 170
    },
    {
      "epoch": 0.1109701965757768,
      "grad_norm": 0.17533652484416962,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.9843,
      "step": 175
    },
    {
      "epoch": 0.11414077362079898,
      "grad_norm": 0.1228385716676712,
      "learning_rate": 6.464113856382752e-05,
      "loss": 1.0515,
      "step": 180
    },
    {
      "epoch": 0.11731135066582118,
      "grad_norm": 0.14011158049106598,
      "learning_rate": 6.259890306925627e-05,
      "loss": 1.0196,
      "step": 185
    },
    {
      "epoch": 0.12048192771084337,
      "grad_norm": 0.11966598778963089,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 1.0158,
      "step": 190
    },
    {
      "epoch": 0.12365250475586556,
      "grad_norm": 0.12233228981494904,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 1.0214,
      "step": 195
    },
    {
      "epoch": 0.12682308180088775,
      "grad_norm": 0.15925836563110352,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 0.9805,
      "step": 200
    },
    {
      "epoch": 0.12682308180088775,
      "eval_loss": 1.0016076564788818,
      "eval_runtime": 19.1852,
      "eval_samples_per_second": 138.44,
      "eval_steps_per_second": 17.305,
      "step": 200
    },
    {
      "epoch": 0.12999365884590997,
      "grad_norm": 0.1137436106801033,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 1.0578,
      "step": 205
    },
    {
      "epoch": 0.13316423589093215,
      "grad_norm": 0.15316516160964966,
      "learning_rate": 5.212206015980742e-05,
      "loss": 1.0016,
      "step": 210
    },
    {
      "epoch": 0.13633481293595434,
      "grad_norm": 0.1435774564743042,
      "learning_rate": 5e-05,
      "loss": 1.0119,
      "step": 215
    },
    {
      "epoch": 0.13950538998097653,
      "grad_norm": 0.12810681760311127,
      "learning_rate": 4.78779398401926e-05,
      "loss": 1.0204,
      "step": 220
    },
    {
      "epoch": 0.14267596702599875,
      "grad_norm": 0.17897763848304749,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.9554,
      "step": 225
    },
    {
      "epoch": 0.14584654407102093,
      "grad_norm": 0.11986444145441055,
      "learning_rate": 4.364910901265606e-05,
      "loss": 1.0419,
      "step": 230
    },
    {
      "epoch": 0.14901712111604312,
      "grad_norm": 0.14275012910366058,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 0.9827,
      "step": 235
    },
    {
      "epoch": 0.1521876981610653,
      "grad_norm": 0.1263553500175476,
      "learning_rate": 3.94660365002137e-05,
      "loss": 0.9867,
      "step": 240
    },
    {
      "epoch": 0.1553582752060875,
      "grad_norm": 0.129071444272995,
      "learning_rate": 3.740109693074375e-05,
      "loss": 1.0307,
      "step": 245
    },
    {
      "epoch": 0.15852885225110971,
      "grad_norm": 0.17482073605060577,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 0.9505,
      "step": 250
    },
    {
      "epoch": 0.1616994292961319,
      "grad_norm": 0.12286773324012756,
      "learning_rate": 3.334301026289712e-05,
      "loss": 1.0503,
      "step": 255
    },
    {
      "epoch": 0.1648700063411541,
      "grad_norm": 0.14134164154529572,
      "learning_rate": 3.135717611098458e-05,
      "loss": 1.0074,
      "step": 260
    },
    {
      "epoch": 0.16804058338617628,
      "grad_norm": 0.12728744745254517,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 1.0242,
      "step": 265
    },
    {
      "epoch": 0.17121116043119847,
      "grad_norm": 0.13187004625797272,
      "learning_rate": 2.748981275911633e-05,
      "loss": 1.0307,
      "step": 270
    },
    {
      "epoch": 0.17438173747622068,
      "grad_norm": 0.17565838992595673,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.9366,
      "step": 275
    },
    {
      "epoch": 0.17755231452124287,
      "grad_norm": 0.13768121600151062,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 1.04,
      "step": 280
    },
    {
      "epoch": 0.18072289156626506,
      "grad_norm": 0.1363866627216339,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 0.9886,
      "step": 285
    },
    {
      "epoch": 0.18389346861128725,
      "grad_norm": 0.12631961703300476,
      "learning_rate": 2.026834118478567e-05,
      "loss": 0.9804,
      "step": 290
    },
    {
      "epoch": 0.18706404565630944,
      "grad_norm": 0.13421660661697388,
      "learning_rate": 1.858900013521788e-05,
      "loss": 1.0136,
      "step": 295
    },
    {
      "epoch": 0.19023462270133165,
      "grad_norm": 0.18205901980400085,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 0.9499,
      "step": 300
    },
    {
      "epoch": 0.19023462270133165,
      "eval_loss": 0.9843480587005615,
      "eval_runtime": 19.1337,
      "eval_samples_per_second": 138.813,
      "eval_steps_per_second": 17.352,
      "step": 300
    },
    {
      "epoch": 0.19340519974635384,
      "grad_norm": 0.13463397324085236,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 1.0141,
      "step": 305
    },
    {
      "epoch": 0.19657577679137603,
      "grad_norm": 0.14523600041866302,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 1.0001,
      "step": 310
    },
    {
      "epoch": 0.19974635383639822,
      "grad_norm": 0.12357877194881439,
      "learning_rate": 1.246638473736378e-05,
      "loss": 0.9864,
      "step": 315
    },
    {
      "epoch": 0.20291693088142043,
      "grad_norm": 0.13752178847789764,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 1.0041,
      "step": 320
    },
    {
      "epoch": 0.20608750792644262,
      "grad_norm": 0.1824190616607666,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.9436,
      "step": 325
    },
    {
      "epoch": 0.2092580849714648,
      "grad_norm": 0.12865875661373138,
      "learning_rate": 8.574517537807897e-06,
      "loss": 1.0217,
      "step": 330
    },
    {
      "epoch": 0.212428662016487,
      "grad_norm": 0.15531201660633087,
      "learning_rate": 7.423543113334436e-06,
      "loss": 0.9834,
      "step": 335
    },
    {
      "epoch": 0.21559923906150918,
      "grad_norm": 0.12426929920911789,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.9877,
      "step": 340
    },
    {
      "epoch": 0.2187698161065314,
      "grad_norm": 0.12803547084331512,
      "learning_rate": 5.353707092521582e-06,
      "loss": 1.0057,
      "step": 345
    },
    {
      "epoch": 0.2219403931515536,
      "grad_norm": 0.17463678121566772,
      "learning_rate": 4.43857548059321e-06,
      "loss": 0.9487,
      "step": 350
    },
    {
      "epoch": 0.22511097019657578,
      "grad_norm": 0.13055680692195892,
      "learning_rate": 3.605548635174533e-06,
      "loss": 1.0346,
      "step": 355
    },
    {
      "epoch": 0.22828154724159797,
      "grad_norm": 0.1539195328950882,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.9981,
      "step": 360
    },
    {
      "epoch": 0.23145212428662015,
      "grad_norm": 0.1287969946861267,
      "learning_rate": 2.191663263037458e-06,
      "loss": 0.9805,
      "step": 365
    },
    {
      "epoch": 0.23462270133164237,
      "grad_norm": 0.1369285136461258,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.9991,
      "step": 370
    },
    {
      "epoch": 0.23779327837666456,
      "grad_norm": 0.1922837644815445,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.9336,
      "step": 375
    },
    {
      "epoch": 0.24096385542168675,
      "grad_norm": 0.1307961642742157,
      "learning_rate": 7.192044826145771e-07,
      "loss": 1.0227,
      "step": 380
    },
    {
      "epoch": 0.24413443246670893,
      "grad_norm": 0.13622573018074036,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.9901,
      "step": 385
    },
    {
      "epoch": 0.24730500951173112,
      "grad_norm": 0.12565191090106964,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 0.9686,
      "step": 390
    },
    {
      "epoch": 0.25047558655675334,
      "grad_norm": 0.1302589774131775,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 0.9999,
      "step": 395
    },
    {
      "epoch": 0.2536461636017755,
      "grad_norm": 0.18174053728580475,
      "learning_rate": 0.0,
      "loss": 0.9485,
      "step": 400
    },
    {
      "epoch": 0.2536461636017755,
      "eval_loss": 0.9816142916679382,
      "eval_runtime": 19.1088,
      "eval_samples_per_second": 138.994,
      "eval_steps_per_second": 17.374,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2841786469567693e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}